appvoid commited on
Commit
01a92a3
·
verified ·
1 Parent(s): d872339

Update TensorBoard training metrics

Browse files
metrics/void-byte-v1/1790868774355361490-de221e1d/eval.jsonl CHANGED
@@ -1,3 +1,4 @@
1
  {"step": 445000, "seed_holdout": {"answer_byte_loss": 0.4232070924564359, "teacher_forced_byte_accuracy": 0.8760330578512396, "generation_exact_match": 0.75, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.3276531007554797, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
2
  {"step": 450000, "seed_holdout": {"answer_byte_loss": 0.1676441727240747, "teacher_forced_byte_accuracy": 0.9504132231404959, "generation_exact_match": 0.5, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5916567484537762, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
3
  {"step": 455000, "seed_holdout": {"answer_byte_loss": 1.8744227794048034, "teacher_forced_byte_accuracy": 0.5131578947368421, "generation_exact_match": 0.25, "generation_truncated": 4, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.2062032911512586, "teacher_forced_byte_accuracy": 0.35555555555555557, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
 
 
1
  {"step": 445000, "seed_holdout": {"answer_byte_loss": 0.4232070924564359, "teacher_forced_byte_accuracy": 0.8760330578512396, "generation_exact_match": 0.75, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.3276531007554797, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
2
  {"step": 450000, "seed_holdout": {"answer_byte_loss": 0.1676441727240747, "teacher_forced_byte_accuracy": 0.9504132231404959, "generation_exact_match": 0.5, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5916567484537762, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}}
3
  {"step": 455000, "seed_holdout": {"answer_byte_loss": 1.8744227794048034, "teacher_forced_byte_accuracy": 0.5131578947368421, "generation_exact_match": 0.25, "generation_truncated": 4, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.2062032911512586, "teacher_forced_byte_accuracy": 0.35555555555555557, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
4
+ {"step": 460000, "seed_holdout": {"answer_byte_loss": 0.47489946377849995, "teacher_forced_byte_accuracy": 0.868995633187773, "generation_exact_match": 0.08333333333333333, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.1246050516764323, "teacher_forced_byte_accuracy": 0.18888888888888888, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}}
metrics/void-byte-v1/eval.jsonl CHANGED
@@ -1,3 +1,4 @@
1
  {"step": 445000, "seed_holdout": {"answer_byte_loss": 0.4232070924564359, "teacher_forced_byte_accuracy": 0.8760330578512396, "generation_exact_match": 0.75, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.3276531007554797, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 18}, {"group": "seed_holdout", "family": "gen_filter_constraints", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_table_aggregate", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_multi_key_sort", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_reference_resolution", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_instruction_override", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_output_schema", "surface": "instruction_json", "exact": true, "generated_bytes": 43, "target_bytes": 43}, {"group": "seed_holdout", "family": "gen_boolean_formula", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_set_expression", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_bounded_arithmetic", "surface": "instruction_json", "exact": false, "generated_bytes": 2, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_text_span_extract", "surface": "instruction_json", "exact": true, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_counterfactual_state", "surface": "instruction_json", "exact": false, "generated_bytes": 26, "target_bytes": 26}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 24, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
2
  {"step": 450000, "seed_holdout": {"answer_byte_loss": 0.1676441727240747, "teacher_forced_byte_accuracy": 0.9504132231404959, "generation_exact_match": 0.5, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5916567484537762, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_ambiguity_detection", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_multi_step_word_problem", "surface": "instruction_json", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_compare_entities", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_missing_information", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_string_normalization", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_list_zip", "surface": "instruction_json", "exact": false, "generated_bytes": 26, "target_bytes": 20}, {"group": "seed_holdout", "family": "gen_entailment_closed_world", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_periodic", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_mirror", "surface": "symbolic", "exact": true, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_cardinality_grounding", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_successor_chain", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_motif_growth", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 45}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 12, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
3
  {"step": 455000, "seed_holdout": {"answer_byte_loss": 1.8744227794048034, "teacher_forced_byte_accuracy": 0.5131578947368421, "generation_exact_match": 0.25, "generation_truncated": 4, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.2062032911512586, "teacher_forced_byte_accuracy": 0.35555555555555557, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_latent_arithmetic", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_sequence_transform", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_binary_set_logic", "surface": "symbolic", "exact": false, "generated_bytes": 5, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_substitution_cipher", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_graph_reasoning", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_equivalence_classes", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_pointer_chase", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_permutation_algebra", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_stack_machine", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_fsm", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_program_induction", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_rewrite_system", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 34}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
 
 
1
  {"step": 445000, "seed_holdout": {"answer_byte_loss": 0.4232070924564359, "teacher_forced_byte_accuracy": 0.8760330578512396, "generation_exact_match": 0.75, "generation_truncated": 0, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.3276531007554797, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 18}, {"group": "seed_holdout", "family": "gen_filter_constraints", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_table_aggregate", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_multi_key_sort", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_reference_resolution", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_instruction_override", "surface": "instruction_json", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_output_schema", "surface": "instruction_json", "exact": true, "generated_bytes": 43, "target_bytes": 43}, {"group": "seed_holdout", "family": "gen_boolean_formula", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_set_expression", "surface": "instruction_json", "exact": true, "generated_bytes": 4, "target_bytes": 4}, {"group": "seed_holdout", "family": "gen_bounded_arithmetic", "surface": "instruction_json", "exact": false, "generated_bytes": 2, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_text_span_extract", "surface": "instruction_json", "exact": true, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_counterfactual_state", "surface": "instruction_json", "exact": false, "generated_bytes": 26, "target_bytes": 26}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 24, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
2
  {"step": 450000, "seed_holdout": {"answer_byte_loss": 0.1676441727240747, "teacher_forced_byte_accuracy": 0.9504132231404959, "generation_exact_match": 0.5, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.5916567484537762, "teacher_forced_byte_accuracy": 0.2777777777777778, "generation_exact_match": 0.0, "generation_truncated": 1, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_ambiguity_detection", "surface": "instruction_json", "exact": true, "generated_bytes": 12, "target_bytes": 12}, {"group": "seed_holdout", "family": "gen_multi_step_word_problem", "surface": "instruction_json", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_compare_entities", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_missing_information", "surface": "instruction_json", "exact": true, "generated_bytes": 6, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_string_normalization", "surface": "instruction_json", "exact": true, "generated_bytes": 10, "target_bytes": 10}, {"group": "seed_holdout", "family": "gen_list_zip", "surface": "instruction_json", "exact": false, "generated_bytes": 26, "target_bytes": 20}, {"group": "seed_holdout", "family": "gen_entailment_closed_world", "surface": "instruction_json", "exact": true, "generated_bytes": 8, "target_bytes": 8}, {"group": "seed_holdout", "family": "gen_periodic", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_mirror", "surface": "symbolic", "exact": true, "generated_bytes": 3, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_cardinality_grounding", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_successor_chain", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_motif_growth", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 45}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 12, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
3
  {"step": 455000, "seed_holdout": {"answer_byte_loss": 1.8744227794048034, "teacher_forced_byte_accuracy": 0.5131578947368421, "generation_exact_match": 0.25, "generation_truncated": 4, "episodes": 12}, "composition_ood": {"answer_byte_loss": 2.2062032911512586, "teacher_forced_byte_accuracy": 0.35555555555555557, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_latent_arithmetic", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_sequence_transform", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_binary_set_logic", "surface": "symbolic", "exact": false, "generated_bytes": 5, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_substitution_cipher", "surface": "symbolic", "exact": false, "generated_bytes": 8, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_graph_reasoning", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_equivalence_classes", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_pointer_chase", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_permutation_algebra", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_stack_machine", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_fsm", "surface": "symbolic", "exact": true, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_program_induction", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 5}, {"group": "seed_holdout", "family": "gen_rewrite_system", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 34}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 6, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
4
+ {"step": 460000, "seed_holdout": {"answer_byte_loss": 0.47489946377849995, "teacher_forced_byte_accuracy": 0.868995633187773, "generation_exact_match": 0.08333333333333333, "generation_truncated": 1, "episodes": 12}, "composition_ood": {"answer_byte_loss": 3.1246050516764323, "teacher_forced_byte_accuracy": 0.18888888888888888, "generation_exact_match": 0.0, "generation_truncated": 2, "episodes": 3}, "families": [{"group": "seed_holdout", "family": "gen_transducer", "surface": "symbolic", "exact": false, "generated_bytes": 4, "target_bytes": 6}, {"group": "seed_holdout", "family": "gen_operator_composition", "surface": "symbolic", "exact": false, "generated_bytes": 2, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_nested_binding", "surface": "symbolic", "exact": false, "generated_bytes": 1, "target_bytes": 2}, {"group": "seed_holdout", "family": "gen_cellular_1d", "surface": "symbolic", "exact": false, "generated_bytes": 9, "target_bytes": 9}, {"group": "seed_holdout", "family": "gen_particle_1d", "surface": "symbolic", "exact": false, "generated_bytes": 17, "target_bytes": 21}, {"group": "seed_holdout", "family": "gen_acceleration_1d", "surface": "symbolic", "exact": false, "generated_bytes": 25, "target_bytes": 24}, {"group": "seed_holdout", "family": "gen_grid_transform", "surface": "symbolic", "exact": false, "generated_bytes": 16, "target_bytes": 13}, {"group": "seed_holdout", "family": "gen_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 31, "target_bytes": 31}, {"group": "seed_holdout", "family": "gen_multi_particle_2d", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 64}, {"group": "seed_holdout", "family": "gen_path_planning", "surface": "symbolic", "exact": false, "generated_bytes": 5, "target_bytes": 3}, {"group": "seed_holdout", "family": "gen_tiny_vm", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 7}, {"group": "seed_holdout", "family": "gen_recursive_blocks", "surface": "symbolic", "exact": true, "generated_bytes": 47, "target_bytes": 47}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 18}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 7, "target_bytes": 56}, {"group": "composition_ood", "family": "compositional_execution", "surface": "symbolic", "exact": false, "generated_bytes": 192, "target_bytes": 16}]}
runs/void-byte-v1/events.out.tfevents.1790868774.f92f6aaf-743a-4c24-a54a-850bd75954cb-8js8b.612.0.1790868774355361490-de221e1d CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bce7673bd2ae1aad42589fce09f00b633108020b5d66f2bed2d1b60df03db5b
3
- size 421878
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3f3bd11b3a20baefe21f6bfdac4bf0682c7c1cd23f4a03db47da1fc443f7e3f
3
+ size 422661